Transcript Introduction to EC

Introduction to
Evolutionary
Computation
The EvoNet Flying Circus
Brought to you by (insert your name)
The EvoNet Training Committee
EvoNet Flying Circus
Q What is the most powerful
problem solver in the
Universe?
 The (human) brain
that created “the wheel, New York, wars and so on”
(after
Douglas Adams)
 The evolution mechanism
created the human brain (after Darwin et al.)
EvoNet Flying Circus
that
Building problem solvers by looking at
and mimicking:
 neurocomputing

brains

evolution  evolutionary computing
EvoNet Flying Circus
Table of Contents






Taxonomy and History
The Metaphor
The Evolutionary Mechanism
Domains of Application
Performance
Sources of Information
EvoNet Flying Circus
Taxonomy
COMPUTATIONAL
INTELLIGENCE
or
SOFT COMPUTING
Neural
Networks
Evolutionary
Programming
Evolutionary
Algorithms
Evolution
Strategies
Fuzzy
Systems
Genetic
Algorithms
EvoNet Flying Circus
Genetic
Programming
History




L. Fogel 1962 (San Diego, CA): Evolutionary
Programming
J. Holland 1962 (Ann Arbor, MI):
Genetic Algorithms
I. Rechenberg & H.-P. Schwefel 1965 (Berlin,
Germany): Evolution Strategies
J. Koza 1989 (Palo Alto, CA):
Genetic Programming
EvoNet Flying Circus
The Metaphor
EVOLUTION
PROBLEM SOLVING
Individual
Fitness
Environment
Candidate Solution
Quality
Problem
EvoNet Flying Circus
The Ingredients
t
reproduction
selection
mutation
recombination
EvoNet Flying Circus
t+1
The Evolution Mechanism

Increasing diversity by
genetic operators
 mutation
 recombination

Decreasing diversity by
selection
 of parents
 of survivors
EvoNet Flying Circus
The Evolutionary Cycle
Selection
Parents
Recombination
Population
Mutation
Replacement
Offspring
EvoNet Flying Circus
Domains of Application







Numerical, Combinatorial Optimisation
System Modeling and Identification
Planning and Control
Engineering Design
Data Mining
Machine Learning
Artificial Life
EvoNet Flying Circus
Performance



Acceptable performance at acceptable costs
on a wide range of problems
Intrinsic parallelism (robustness, fault
tolerance)
Superior to other techniques on complex
problems with



lots of data, many free parameters
complex relationships between parameters
many (local) optima
EvoNet Flying Circus
Advantages







No presumptions w.r.t. problem space
Widely applicable
Low development & application costs
Easy to incorporate other methods
Solutions are interpretable (unlike NN)
Can be run interactively, accommodate user
proposed solutions
Provide many alternative solutions
EvoNet Flying Circus
Disadvantages




No guarantee for optimal solution within finite
time
Weak theoretical basis
May need parameter tuning
Often computationally expensive, i.e. slow
EvoNet Flying Circus
Summary
EVOLUTIONARY COMPUTATION:






is based on biological metaphors
has great practical potentials
is getting popular in many fields
yields powerful, diverse applications
gives high performance against low costs
AND IT’S FUN !
EvoNet Flying Circus